Filters








642 Hits in 7.9 sec

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

Hui Zeng, Jianrui Cai, Lida Li, Zisheng Cao, Lei Zhang
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we learn image-adaptive 3-dimensional lookup tables (3D LUTs) to achieve fast and robust photo enhancement. 3D LUTs are widely used for manipulating color and tone of photos, but they are  ...  We, for the first time to our best knowledge, propose to learn 3D LUTs from annotated data. More importantly, our learned 3D LUT is image-adaptive.  ...  More importantly, our proposed learning architecture can learn image-adaptive 3D LUTs to achieve intelligent and high performance photo enhancement, which cannot be achieved by the current 3D LUT models  ... 
doi:10.1109/tpami.2020.3026740 pmid:32976094 fatcat:3eohl4sq5zhrlebvw2s5xe7ciq

AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement [article]

Canqian Yang, Meiguang Jin, Xu Jia, Yi Xu, Ying Chen
2022 arXiv   pre-print
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice.  ...  Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy.  ...  Canqian Yang is supported in part by Alibaba Group through Alibaba Research Intern Program.  ... 
arXiv:2204.13983v1 fatcat:3wase4wterdlrjvdsbhvzyjdpu

StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement [article]

Yuda Song, Hui Qian, Xin Du
2021 arXiv   pre-print
With a simple one-time setting, users can customize the model to make the enhanced images more in line with their aesthetics.  ...  In this paper, we propose a deep learning-based image enhancement method covering multiple tonal styles using only a single model dubbed StarEnhancer.  ...  In our opinion, a practical image enhancement method should not employ a generic image restoration network but aim to be real-time and style-aware.  ... 
arXiv:2107.12898v3 fatcat:blyfuyjavfawdj4gc525dgxnni

A New Journey from SDRTV to HDRTV [article]

Xiangyu Chen, Zhengwen Zhang, Jimmy S. Ren, Lynhoo Tian, Yu Qiao, Chao Dong
2021 arXiv   pre-print
Base on the analysis, we propose a three-step solution pipeline including adaptive global color mapping, local enhancement and highlight generation.  ...  Moreover, the above analysis inspires us to present a lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping.  ...  Learning image-adaptive 3d lookup tables for high perfor- mance photo enhancement in real-time.  ... 
arXiv:2108.07978v2 fatcat:3o54fdfrdfd5xirvlwdozrjah4

Deep bilateral learning for real-time image enhancement

Michaël Gharbi, Jiawen Chen, Jonathan T. Barron, Samuel W. Hasinoff, Frédo Durand
2017 ACM Transactions on Graphics  
Given a reference imaging pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements and enable real-time evaluation.  ...  Performance is a critical challenge in mobile image processing.  ...  ACKNOWLEDGMENTS We thank the SIGGRAPH reviewers for their constructive comments. Special thanks to Marc Levoy for his valuable feedback. This work was partially funded by Toyota.  ... 
doi:10.1145/3072959.3073592 fatcat:yncqbh5dcvfrzoemodvk7a76pi

Delta Sampling R-BERT for limited data and low-light action recognition [article]

Sanchit Hira, Ritwik Das, Abhinav Modi, Daniil Pakhomov
2021 arXiv   pre-print
We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset.  ...  Most previous works only evaluate performance on large, well illuminated datasets like Kinetics and HMDB51.  ...  [19] introduced data dependent lookup to perform real-time image enhancement on full-resolution images. Yang et al.  ... 
arXiv:2107.05202v1 fatcat:63nizg7egbhtpj7yvdlkarkgsu

2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges

Yuzhen Niu, Yini Zhong, Wenzhong Guo, Yiqing Shi, Peikun Chen
2019 IEEE Access  
Finally, we discuss the challenges for IQA, including the influence of different factors on each other, the performance of IQA metrics in real applications, and the combination of quality assessment, restoration  ...  Image quality is important not only for the viewing experience, but also for the performance of image processing algorithms.  ...  proposed an aesthetics-driven 3D image recomposition method, which can adapt to the depth changes of foreground objects in a given 3D image to enhance human visual aesthetic experience.  ... 
doi:10.1109/access.2018.2885818 fatcat:gjq7vdwczffufmk3smmn7mokgi

Fatigue Detection [article]

Ashish Verma, Ankush Goyal, Davinderjit Kaur
2019 arXiv   pre-print
Nowadays, there are many fatigue detection methods and the majority of them are tracking eye in real-time using one or two cameras to detect the physical responses in eyes.  ...  It is indicated that the responses in eyes have high relativity with driver fatigue. As part of this project, We will propose a fatigue detection system based on pose estimation.  ...  A lookup table is built for a fast access to the silhouettes detected in an image around a given location.  ... 
arXiv:1911.10629v1 fatcat:3dj3kkbqyjfvblmwdh52xpfzba

Imaging and Classification Techniques for Seagrass Mapping and Monitoring: A Comprehensive Survey [article]

Md Moniruzzaman, S. M. Shamsul Islam, Paul Lavery, Mohammed Bennamoun, C. Peng Lam
2019 arXiv   pre-print
, fully automated seagrass detectors that can work in real-time, accurate techniques for estimating the seagrass density, and the availability of high computation facilities for processing large scale  ...  For addressing these gaps, future research should focus on developing cheaper image and video data collection techniques, deep learning based automatic annotation and classification, and real-time percentage-cover  ...  in real time detection and classification.  ... 
arXiv:1902.11114v2 fatcat:cctkhtbc2bg73pfenrkbmxq3ay

Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer [article]

Xide Xia, Meng Zhang, Tianfan Xue, Zheng Sun, Hui Fang, Brian Kulis, Jiawen Chen
2020 arXiv   pre-print
Compared to the state of the art, our method produces visually superior results and is three orders of magnitude faster, enabling real-time performance at 4K on a mobile phone.  ...  We propose a new end-to-end model for photorealistic style transfer that is both fast and inherently generates photorealistic results.  ...  to slow to run in real time on a mobile device.  ... 
arXiv:2004.10955v2 fatcat:7zw4kqopffetxc5oqawijxl53e

Unstructured video-based rendering

Luca Ballan, Gabriel J. Brostow, Jens Puwein, Marc Pollefeys
2010 ACM SIGGRAPH 2010 papers on - SIGGRAPH '10  
First and last images are from real cameras 40 • apart.  ...  The objective is to easily navigate in 3D, generating a video-based rendering (VBR) of a performance filmed with widely separated cameras.  ...  Acknowledgements We thank Ralph Wiedemeier, Davide Scaramuzza, and Mark Rothman whose performances constitute the Juggler, Magician, and Rothman data, Nils Hasler and Jürgen Gall for the Climber videos  ... 
doi:10.1145/1833349.1778824 fatcat:wuzxrqvlyfhqlcuvjhpwoeozlm

Unstructured video-based rendering

Luca Ballan, Gabriel J. Brostow, Jens Puwein, Marc Pollefeys
2010 ACM Transactions on Graphics  
First and last images are from real cameras 40 • apart.  ...  The objective is to easily navigate in 3D, generating a video-based rendering (VBR) of a performance filmed with widely separated cameras.  ...  Acknowledgements We thank Ralph Wiedemeier, Davide Scaramuzza, and Mark Rothman whose performances constitute the Juggler, Magician, and Rothman data, Nils Hasler and Jürgen Gall for the Climber videos  ... 
doi:10.1145/1778765.1778824 fatcat:pyp527gc6ffd7pdvsx6ejr2foy

Unstructured video-based rendering

Luca Ballan, Gabriel J. Brostow, Jens Puwein, Marc Pollefeys
2010 ACM Transactions on Graphics  
First and last images are from real cameras 40 • apart.  ...  The objective is to easily navigate in 3D, generating a video-based rendering (VBR) of a performance filmed with widely separated cameras.  ...  Acknowledgements We thank Ralph Wiedemeier, Davide Scaramuzza, and Mark Rothman whose performances constitute the Juggler, Magician, and Rothman data, Nils Hasler and Jürgen Gall for the Climber videos  ... 
doi:10.1145/1833351.1778824 fatcat:rgn24incizc35mc2hmi26cop2m

Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision [article]

Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal Fua, Oleksandr Sotnychenko, Weipeng Xu, Christian Theobalt
2017 arXiv   pre-print
All in all, we argue that the use of transfer learning of representations in tandem with algorithmic and data contributions is crucial for general 3D body pose estimation.  ...  Using only the existing 3D pose data and 2D pose data, we show state-of-the-art performance on established benchmarks through transfer of learned features, while also generalizing to in-the-wild scenes  ...  poor generalization to real images.  ... 
arXiv:1611.09813v5 fatcat:uka37jvzbzefzow7td73phrfly

EyeOpener

Zhixin Shu, Eli Shechtman, Dimitris Samaras, Sunil Hadap
2016 ACM Transactions on Graphics  
A fully automatic pipeline for realistic eye editing is challenging due to the unconstrained conditions under which the face appears in a typical photo collection.  ...  Our example-based editing approach is robust and effective for realistic image editing.  ...  ACKNOWLEDGMENTS We acknowledge Jianchao Yang and Kalyan Sunkavalli for helpful discussions.  ... 
doi:10.1145/2926713 fatcat:qrxwd435ojhcnh26usvjxqn6im
« Previous Showing results 1 — 15 out of 642 results